DASLab releases GSQ-RCO GGUFs of DeepSeek-V4.1-Flash-1017
The IQ2_XXS build matches the base model’s reported task average, and every build is said to run on a 12 GB GPU with Strata.
34
Organization
Institute of Science and Technology Austria
- Mentions · 7d0
- Mentions · 30d1
- All mentions2
- First seenAug 28, 2026
- Last mentioned17d ago
Timeline
2 articles · newest firstISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF — new model trending #3 on Hugging Face
ISTA-DASLab releases GSQ-RCO non-uniform GGUF quantizations of Qwen3.8-27B down to 2.5 bpw, with task-lossless IQ3_S matching BF16 benchmark scores.
44
Appears with
- Ollamaproduct · 1
- llama.cppproduct · 1
- ISTA-DASLabvendor · 1
- LM Studioproduct · 1
- DASLaborganization · 1
- GSQproduct · 1
- DeepSeek-V4.1-Flash-1017ai model · 1
- Qwen3.8-27Bai model · 1
- Unslothvendor · 1
- RCOproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.